|
|
--- |
|
|
license: mit |
|
|
tags: |
|
|
- pytorch |
|
|
- diffusers |
|
|
- unconditional-audio-generation |
|
|
- diffusion-models-class |
|
|
--- |
|
|
|
|
|
# Model Card for [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class) |
|
|
|
|
|
这个模型是一个旨在生成 electronic 风格音乐的非条件性扩散模型 |
|
|
|
|
|
## Usage |
|
|
|
|
|
```python |
|
|
import torch |
|
|
from diffusers import DiffusionPipeline |
|
|
from IPython.display import Audio |
|
|
|
|
|
|
|
|
device = "cuda" if torch.cuda.is_available() else "cpu" |
|
|
print(f"device: {device}") |
|
|
|
|
|
pipe = DiffusionPipeline.from_pretrained( |
|
|
'Kevin3111/Electronic_test' |
|
|
).to(device) |
|
|
output = pipe(steps=50) |
|
|
|
|
|
display(output.images[0]) |
|
|
display(Audio(output.audios[0], rate=pipe.mel.get_sample_rate())) |
|
|
``` |
|
|
|
